Title | ||
---|---|---|
Combining statistical and syntactical systems for spoken language understanding with graphical models |
Abstract | ||
---|---|---|
There are two basic approaches for semantic processing in spoken language understanding: a rule based approach and a statistic approach. In this paper we combine both of them in a novel way by using statistical and syntactical dynamic bayesian networks (DBNs) together with Graph- ical Models (GMs) for spoken language understanding (SLU). GMs merge in a complex, mathematical way prob- ability with graph theory. This results in four different setups which raise in their complexity. Comparing our results to a baseline system we achieve a F1-measure of 93:7% in word classes and 95:7% in concepts for our best setup in the ATIS-Task. This outperforms the baseline system relatively by 3:7% in word classes and by 8:2% in concepts. The expermiments were performend with the graphical model toolkit (GMTK). Index Terms: natural language understanding, ma- chine learning, graphical models |
Year | Venue | Keywords |
---|---|---|
2008 | INTERSPEECH | dynamic bayesian network,indexing terms,graphical model,semantic processing,rule based,graph theory |
Field | DocType | Citations |
Pattern recognition,Computer science,Natural language processing,Artificial intelligence,Language identification,Graphical model,Linguistics,Spoken language | Conference | 3 |
PageRank | References | Authors |
0.51 | 8 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stefan Schwärzler | 1 | 16 | 2.45 |
Jürgen T. Geiger | 2 | 88 | 6.95 |
joachim f schenk | 3 | 3 | 0.51 |
Marc Al-Hames | 4 | 116 | 8.75 |
Benedikt Hörnler | 5 | 120 | 9.61 |
Günther Ruske | 6 | 154 | 36.13 |
Gerhard Rigoll | 7 | 2788 | 268.87 |
technische universitat munchen | 8 | 11 | 2.44 |